paper-with-me

홈 › Papers

Large Language Model Recall Uncertainty is Modulated by the Fan Effect

2024-07-08 · Jesse Roberts, Kyle Moore, Thao Pham, Oseremhen Ewaleifoh, Doug Fisher

This paper evaluates whether large language models (LLMs) exhibit cognitive fan effects, similar to those discovered by Anderson in humans, after being pre-trained on human textual data. We conduct two sets of in-context recall experiments designed to elicit fan effects. Consistent with human results, we find that LLM recall uncertainty, measured via token probability, is influenced by the fan effect. Our results show that removing uncertainty disrupts the observed effect. The experiments suggest the fan effect is consistent whether the fan value is induced in-context or in the pre-training data. Finally, these findings provide in-silico evidence that fan effects and typicality are expressions of the same phenomena.

📄 PDF Abstract BibTeX arXiv:2407.06349

Code (1)

JesseTNRoberts/Large-Language-Model-Recall-Uncertainty-is-Modulated-by-the-Fan-Effect 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Confidence-Modulated Speculative Decoding for Large Language Models

2025-08-21 · Jaydip Sen, Subhasis Dasgupta, Hetvi Waghela arxiv

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static draftin…

Machine Translation

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

2025-05-19 · Sungmin Cha, Kyunghyun Cho

Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented--enabling smaller st…

Knowledge DistillationLanguage ModelingLanguage Modelling

Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty

2026-05-29 · Kyle Moore, Jesse Roberts, Daryl Watson, William Ward 외 arxiv

Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis. Primarily to recognize and combat hallucination, the field has largely focused on measuring and improving calibratio…

Lightweight Transformer Framework for Weakly Supervised Semantic Segmentation

2025-11-24 · Ali Torabi, Sanjog Gaihre, Yaqoob Majeed arxiv

Weakly supervised semantic segmentation (WSSS) must learn dense masks from noisy, under-specified cues. We revisit the SegFormer decoder and show that three small, synergistic changes make weak supervision markedly more …

Semantic Segmentation

Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning

2026-06-04 · Ujjwal Bhatta, Utsabi Dangol, Sumaly Bajracharya, Rodrigue Rizk 외 arxiv

Sparse rewards and heterogeneous task sequences remain persistent challenges in Reinforcement Learning (RL), often resulting in slow convergence, weak generalization, and inefficient exploration. We propose Uncertainty-A…

Reinforcement Learning